🛠 Tech Stack

💼 About This Role

You'll own the full LLM pipeline from data preparation to production, focusing on optimizing customer service scheduling through innovative AI solutions. You will develop and refine large language models to extract actionable insights and improve business decision-making.

🎯 What You'll Do

• Design and iterate prompts for LLM utility and safety across products.
• Build and maintain Retrieval-Augmented Generation QA systems.
• Develop multi-agent LLM architectures with LangGraph or similar.
• Collaborate with product and CS teams to integrate AI into chatbots.

📋 Requirements

• Master's degree in CS, Data Science or related field.
• 2+ years deep-learning/NLP experience with 1+ year in LLM work.
• Prompt engineering expertise including few-shot and structured prompting.
• Experience building multi-agent LLM workflows with agent orchestration.

✨ Nice to Have

• Published AI research or tech blogs.
• Experience with vLLM or SGLang inference architectures.

🎁 Benefits & Perks

• 🏖️ Flexible remote work
• 💰 Competitive salary
• 📈 Career growth opportunities
• 🩺 Health insurance
• 🌍 International team exposure

🚩 Heads Up

• Combines senior title with only 2+ years experience requirement.
• Broad responsibilities: full LLM pipeline, prompt engineering, multi-agent systems, evaluation, collaboration.
• Requirements list includes multiple soft skills (self-driven, eager to learn) that are not hard dealbreakers.